Deep Learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge

no code implementations • 9 Aug 2021 • Alain Lalande, Zhihao Chen, Thibaut Pommier, Thomas Decourselle, Abdul Qayyum, Michel Salomon, Dominique Ginhac, Youssef Skandarani, Arnaud Boucher, Khawla Brahim, Marleen de Bruijne, Robin Camarasa, Teresa M. Correia, Xue Feng, Kibrom B. Girum, Anja Hennemuth, Markus Huellebrand, Raabid Hussain, Matthias Ivantsits, Jun Ma, Craig Meyer, Rishabh Sharma, Jixi Shi, Nikolaos V. Tsekos, Marta Varela, Xiyue Wang, Sen yang, Hannu Zhang, Yichi Zhang, Yuncheng Zhou, Xiahai Zhuang, Raphael Couturier, Fabrice Meriaudeau

The publicly available database consists of 150 exams divided into 50 cases with normal MRI after injection of a contrast agent and 100 cases with myocardial infarction (and then with a hyperenhanced area on DE-MRI), whatever their inclusion in the cardiac emergency department.

Deep Learning Based Cardiac MRI Segmentation: Do We Need Experts?

no code implementations • 23 Jul 2021 • Youssef Skandarani, Pierre-Marc Jodoin, Alain Lalande

Results reveal that generalization performances of a segmentation neural network trained on non-expert groundtruth data is, to all practical purposes, as good as on expert groundtruth data, in particular when the non-expert gets a decent level of training, highlighting an opportunity for the efficient and cheap creation of annotations for cardiac datasets.

MRI segmentation Segmentation

GANs for Medical Image Synthesis: An Empirical Study

no code implementations • 11 May 2021 • Youssef Skandarani, Pierre-Marc Jodoin, Alain Lalande

The top-performing GANs are capable of generating realistic-looking medical images by FID standards that can fool trained experts in a visual Turing test and comply to some metrics.

Image Generation Medical Image Generation

Neural Teleportation

1 code implementation • 2 Dec 2020 • Marco Armenta, Thierry Judge, Nathan Painchaud, Youssef Skandarani, Carl Lemaire, Gabriel Gibeau Sanchez, Philippe Spino, Pierre-Marc Jodoin

In this paper, we explore a process called neural teleportation, a mathematical consequence of applying quiver representation theory to neural networks.

Position

Automatic Myocardial Infarction Evaluation from Delayed-Enhancement Cardiac MRI using Deep Convolutional Networks

no code implementations • 30 Oct 2020 • Kibrom Berihu Girum, Youssef Skandarani, Raabid Hussain, Alexis Bozorg Grayeli, Gilles Créhange, Alain Lalande

The second network is used to segment the pathological areas such as myocardial infarction, myocardial no-reflow, and normal myocardial region.

Cardiac Segmentation with Strong Anatomical Guarantees

1 code implementation • 15 Jun 2020 • Nathan Painchaud, Youssef Skandarani, Thierry Judge, Olivier Bernard, Alain Lalande, Pierre-Marc Jodoin

In this paper, we present a framework for producing cardiac image segmentation maps that are guaranteed to respect pre-defined anatomical criteria, while remaining within the inter-expert variability.

Cardiac Segmentation Image Segmentation +3

On the effectiveness of GAN generated cardiac MRIs for segmentation

no code implementations • MIDL 2019 • Youssef Skandarani, Nathan Painchaud, Pierre-Marc Jodoin, Alain Lalande

On one side of our model is a Variational Autoencoder (VAE) trained to learn the latent representations of cardiac shapes.

Cardiac Segmentation Data Augmentation

Cardiac MRI Segmentation with Strong Anatomical Guarantees

1 code implementation • 5 Jul 2019 • Nathan Painchaud, Youssef Skandarani, Thierry Judge, Olivier Bernard, Alain Lalande, Pierre-Marc Jodoin

In this paper, we propose a cardiac MRI segmentation method which always produces anatomically plausible results.

Cardiac Segmentation MRI segmentation +2